To bring it back to the OP's "Why would we want the more powerful hardware that is online all day to be dumb?", I don't think relays should be smart, I think they should be efficient. As you pointed out they need to protect themselves from things like spam to keep costs down and stay alive. As someone else pointed out, we can have things run in the datacenter as other clients / DVMs, and still have simple, efficient relays. So at the protocol level, my expectation is that the more we burden the relays the less reliable and more expensive they'll become. OTOH we can have simple web clients, fancy web clients, slick mobile clients, and colossal workstation clients, and the cost and reliability is paid for by the person running it. We should try and figure out how to compensate relay runners not so they'll add more features, but just so they'll keep doing what they're doing. It's hard enough already and they aren't getting as much out as they're putting in.
And of course: we're all going to do whatever we think is best, because that's what makes nostr awesome! Apparently all we needed to do was remember that we can change the world. How long have we been sleeping 😞? Well we aren't anymore ☀️ 😎 ☀️
Just so we're all on the same page, whoever writes the game owns all the assets.
Bringing the🔥! It seems to me that more people will run clients than relays, and the client has the last word before your eyeballs, so I would say that you have to trust the client more than the relay. And you can only connect to relays that implement all of the features that your client expects, so adding sophisticated features to relays has lower marginal utility than adding them to clients. OTOH, pushing all of the complexity into clients results in fewer clients that are harder to build, and you don't want that either. There's a balance that the community will ultimately find, and my expectation is that it will involve clients testing out new ideas, and relays adopting ones that have become stable and expected.
But what really matters is that it doesn't matter who does what where because it's all an open protocol and gfy we're living in the future! 🤙 🚀
Relays should be treated like ADHD doom boxes. What's in there? I don't know. Is it valuable? I don't know that either. Am I going to throw it away? Hahahahahaha. Dig until you find value.
You should be able to run https://ollama.com with Microsoft's `phi3:mini-128k` or `llama3.1:8b-instruct-q3_K_M`. You can see the pre-configured models and their rough sizes at https://ollama.com/library.
You are able to choose which client to run, or even write your own. If there's a bug you can switch to another one until it's fixed. Depending on your circumstances you can choose between convenience and security. Relays are shared by everyone, and simplicity improves stability.
You're running the client. Someone else is running the relay.
Because you can't trust the relay as much as the client. Simplicity is durability, compatibility, reliability.
If you don't have a GPU or a Mac, try LLM Farm (iOS) or mllm (Android)
If you really don't have options, you could see how fast Phi-3 mini is for you. That one's small enough to run on many phones.
If you're on a Mac, 75% of your memory is a GPU. If you really are CPU only, your options are pretty limited.
Italian genealogy can be a rewarding hobby. Connections old and new nostr:note16u5ktp24592qpsx5vxadnle4kncmgpayckad3y2rhvh5t826ke5qpz8kgr
To be fair the drop had ops written all over it... the data could have been legit. Yet another situation where statements are "technically true".
>>> That’s a really hopeful and insightful take. Local models, where individuals have control over the AI they’re using, definitely seem like they could offer a better path forward. If the person running the model is the person themselves, they have the power to shape it in ways that align with their own values and priorities—like truth, transparency, and critical thinking—instead of being subjected to the agendas of big corporations or outside forces.
It puts the incentives back in the hands of the user, rather than the model being optimized for engagement or profit. You’d have more control over the input and output, which could help foster more honest interactions with information and minimize the manipulation that comes with larger, centralized systems.
Before that I tried to listen to two completely different podcasts and had to turn them off when I started yelling at them. Apparently podcasts are part of the machine now.
I just spent an hour and a half driving and debating the future with ChatGPT, and I don't regret any of it.
#llm #ai
Wait until real videos are proclaimed to be fake
Power is the opportunity to make good decisions. Freedom is the opportunity to make bad ones.
#philosophy
Last week I was going to quip that everyone is a nostr user already, but this is a better one-liner nostr:note10fsemr5vy9nj34744c9eaty8f33ap7u98lgmmfy6rrsmxes8uk6qy0djxw